# Package for approximate small quantiles
**URL:** https://discourse.julialang.org/t/package-for-approximate-small-quantiles/20046
**Category:** General Usage
**Tags:** statistics, packages
**Created:** [January 24, 2019, 5:12pm UTC](https://discourse.julialang.org/t/package-for-approximate-small-quantiles/20046 "2019-01-24T17:12:28Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@heliosdrm](https://discourse.julialang.org/u/heliosdrm)
#### Post date: [January 24, 2019, 5:12pm UTC](https://discourse.julialang.org/t/package-for-approximate-small-quantiles/20046/1 "2019-01-24T17:12:28Z")
Anybody knows about a package that might be used for fast estimation of approximated quantiles? I’m looking for an efficient method that might be used with very large datasets, without having to store all the values (I can obtain them with an iterator). E.g. Greenwald’s and Khanna’s method ([https://doi.org/10.1145/375663.375670](https://doi.org/10.1145/375663.375670)), or perhaps Cormode’s et al. ([Effective computation of biased quantiles over data streams | IEEE Conference Publication | IEEE Xplore](https://doi.org/10.1109/ICDE.2005.55)), or any other that works nice with small quantiles (around q=0.05).
---
### Author:  [@simonbyrne](https://discourse.julialang.org/u/simonbyrne)
#### Post date: [January 24, 2019, 6:30pm UTC](https://discourse.julialang.org/t/package-for-approximate-small-quantiles/20046/2 "2019-01-24T18:30:33Z")
Try [OnlineStats.jl](https://github.com/joshday/OnlineStats.jl):
- [https://joshday.github.io/OnlineStats.jl/stable/api.html#OnlineStats.Quantile](https://joshday.github.io/OnlineStats.jl/stable/api.html#OnlineStats.Quantile)
- [https://joshday.github.io/OnlineStats.jl/stable/api.html#OnlineStats.P2Quantile](https://joshday.github.io/OnlineStats.jl/stable/api.html#OnlineStats.P2Quantile)